TY - GEN
T1 - Lost Shopping! Monocular Localization in Large Indoor Spaces
AU - Wang, Shenlong
AU - Fidler, Sanja
AU - Urtasun, Raquel
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/2/17
Y1 - 2015/2/17
N2 - In this paper we propose a novel approach to localization in very large indoor spaces (i.e., 200+ store shopping malls) that takes a single image and a floor plan of the environment as input. We formulate the localization problem as inference in a Markov random field, which jointly reasons about text detection (localizing shop's names in the image with precise bounding boxes), shop facade segmentation, as well as camera's rotation and translation within the entire shopping mall. The power of our approach is that it does not use any prior information about appearance and instead exploits text detections corresponding to the shop names. This makes our method applicable to a variety of domains and robust to store appearance variation across countries, seasons, and illumination conditions. We demonstrate the performance of our approach in a new dataset we collected of two very large shopping malls, and show the power of holistic reasoning.
AB - In this paper we propose a novel approach to localization in very large indoor spaces (i.e., 200+ store shopping malls) that takes a single image and a floor plan of the environment as input. We formulate the localization problem as inference in a Markov random field, which jointly reasons about text detection (localizing shop's names in the image with precise bounding boxes), shop facade segmentation, as well as camera's rotation and translation within the entire shopping mall. The power of our approach is that it does not use any prior information about appearance and instead exploits text detections corresponding to the shop names. This makes our method applicable to a variety of domains and robust to store appearance variation across countries, seasons, and illumination conditions. We demonstrate the performance of our approach in a new dataset we collected of two very large shopping malls, and show the power of holistic reasoning.
UR - http://www.scopus.com/inward/record.url?scp=84973862342&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84973862342&partnerID=8YFLogxK
U2 - 10.1109/ICCV.2015.309
DO - 10.1109/ICCV.2015.309
M3 - Conference contribution
AN - SCOPUS:84973862342
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 2695
EP - 2703
BT - 2015 International Conference on Computer Vision, ICCV 2015
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 15th IEEE International Conference on Computer Vision, ICCV 2015
Y2 - 11 December 2015 through 18 December 2015
ER -